Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Time-Series Representation Feature Refinement with a Learnable Masking Augmentation Framework in Contrastive Learning.

Sensors (Basel, Switzerland)·2025
Same author

Cognitive Refined Augmentation for Video Anomaly Detection in Weak Supervision.

Sensors (Basel, Switzerland)·2024
Same author

Sound Event Detection by Pseudo-Labeling in Weakly Labeled Dataset.

Sensors (Basel, Switzerland)·2021
Same author

Seismic Data Augmentation Based on Conditional Generative Adversarial Networks.

Sensors (Basel, Switzerland)·2020
Same author

Fusion-ConvBERT: Parallel Convolution and BERT Fusion for Speech Emotion Recognition.

Sensors (Basel, Switzerland)·2020
Same author

Mapping Functional Connectivity from the Dorsal Cortex to the Thalamus.

Neuron·2020

Related Experiment Video

Updated: Oct 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Unsupervised domain adaptation based COVID-19 CT infection segmentation network.

Han Chen1, Yifan Jiang1, Murray Loew2

  • 1School of Electrical Engineering, Korea University, Seoul, 02841 South Korea.

Applied Intelligence (Dordrecht, Netherlands)
|November 12, 2021
PubMed
Summary

This study introduces an unsupervised domain adaptation network for segmenting COVID-19 infection areas in CT scans. The method effectively uses synthetic and unlabeled real data to enhance segmentation accuracy, achieving state-of-the-art results.

Keywords:
Adversarial trainingAutomatic segmentationCOVID-19Computed tomographyDomain adaptation

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

558

Related Experiment Videos

Last Updated: Oct 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

558

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate segmentation of COVID-19 infection areas in CT images is crucial for diagnosis.
  • Limited pixel-level annotated medical data hinders the development of precise segmentation models.
  • Existing methods struggle with generalization due to domain discrepancies between datasets.

Purpose of the Study:

  • To develop an unsupervised domain adaptation segmentation network for improved COVID-19 CT image analysis.
  • To address the challenge of limited annotated data by leveraging synthetic and unlabeled real-world data.
  • To enhance the generalization capability of segmentation models for real COVID-19 CT scans.

Main Methods:

  • Proposed an unsupervised domain adaptation segmentation network utilizing synthetic and unlabeled real COVID-19 CT images.
  • Developed a novel domain adaptation module to align synthetic and real data domains.
  • Implemented an unsupervised adversarial training scheme to learn domain-invariant features for robust segmentation.

Main Results:

  • The proposed method achieved state-of-the-art segmentation performance on COVID-19 CT images.
  • Domain adaptation module effectively improved the network's generalization to the real domain.
  • Adversarial training enabled the learning of robust, domain-invariant features for segmentation.

Conclusions:

  • Unsupervised domain adaptation is a viable approach to overcome data limitations in medical image segmentation.
  • The proposed network effectively segments COVID-19 infection areas in CT images, outperforming existing methods.
  • This technique holds promise for improving the diagnostic accuracy and efficiency of COVID-19 detection using CT scans.